A numerical simulation of turbulent natural convection (the Rayleigh–Bénard problem) has been conducted using large-eddy-simulation (LES) methods and the results compared with several experiments. The development of the LES equation is outlined and discussed. The modelling of the small-scale turbulent motion (called subgrid modelling) is also discussed. The resulting LES equations are solved and data collected over a short period of time in a similar manner to the direct simulation of the governing conservation equations. An explicit, second-order accurate, finite-difference scheme is used to solve the equations. Various average properties of the resulting flow field are calculated from the data and compared with experimental data in the literature. The use of a subgrid model allows a higher value of Ra to be simulated than was previously possible with a direct simulation. The highest Ra successfully simulated was 2.5 × 106. The problems at higher values of Ra are discussed and suggestions for improvements made.

While parallel computers o er signi cant computational performance, it is generally necessary to evaluate several programming strategies. Two programming strategies for a fairly common problem|a periodic tridiagonal solver|are developed and evaluated. Simple model calculations as well as timing results are presented to evaluate these strategies.The particular tridiagonal solver evaluated is used in many computational uid dynamic simulation codes. The feature that makes this algorithm unique is that these simulation codes usually require simultaneous solutions for multiple right-hand-sides RHS of the system of equations. Each RHS solutions is independent and thus can becomputed in parallel. Thus, a Gaussian-elimination-type algorithm can be used in a parallel computation and more complicated approaches such as cyclic reduction are not required.The two strategies are a transpose strategy and a distributed solver strategy. For the transpose strategy, the data is moved so that a subset of all the RHS problems is solved on each of the several processors. This usually requires signi cant data movement b e t ween processor memories across a network. The second strategy attempts to have the algorithm follow the data across processor boundaries in a chained manner. This usually requires signi cantly less data movement. An approach to accomplish this second strategy in a near-perfect load-balanced manner is developed. In addition, an algorithm will be shown to directly transform a sequential Gaussian-eliminationtype algorithm into the parallel, chained, load-balanced algorithm.

No abstract

Abstract-The execution environments For scientific applications have evolved significantly over the years. Vector and parallel architectures have provided significantly faster computations. Cluster computers have reduced the cost of high-performance architectures. However, the software development environments have not keep pace. Object-oriented and component-based languages have not been widely adopted. Distributed computing on local area networks and Grids is only being used by a most number of applications.Clearly, there is a need for development environments that support the efficient creation of applications that use modern execution systems. This has been the goal of a continuing research effort over the last several years. The previous focus has been on using component-based ideas to develop a programming model and associated framework to support such a development approach. In this paper, two additional concepts are added to the base approach. Aspect-oriented concepts are applied to support the reduction of intertwined code related to different programming concerns; mixing I/O with a numerical computation is one example. Particularly in large applications, intertwining code can lead to applications that are difficult to modify and to manage. The second concept being added is the use of behavioral metadata. When coupling smaller pieces of code (or components) to make a larger composite application, one needs to determine the suitability of the internal behavior of component as well as the compatibility of its interfaces. The objective is to integrate some of this information into the component and design a framework assist the programmer in making these decisions. I. OBJECTIVE OF TARGET FRAMEWORK A. The Focus for the Programming ModelProgramming efficiency has generally been a problem in the development of scientific applications. [1] [2] Application developers must juggle a number of concerns, which include the correct implementation of algorithms, high performance requirements, and use of large data sets. The need to analyze the output adds other programming aspects, such as the use of graphics routines. The ever changing architecture designs of computers further complicates the scenario. Also, target problems are transitioning from a narrow focus (i.e., the study of an isolated physical phenomenon) to multi-discipline applications where different element applications must interact to correctly capture the target problem. [3] [4] And, the need to share part or all of an application is increasing.Clearly, the development of modular, well-organized applications that are portable is an important goal of most application developers. The use of library packages has traditionally been the means of supporting such a programming requirement. But, many applications still end up with the Old Dominion University, Norfolk, VA University of Tennessee, Knoxville TN 37996 different types of programming aspects coded in an intertwined style which results in applications that are hard to decipher and to manage. The inte...

No abstract